Ai/Llm Engineer

2T Consulting; Maywood (NJ); On-site; USD 130,000 - 190,000; Full time

Job summary

2T Consulting in New Jersey seeks a highly skilled AI/LLM Engineer to design, develop, and deploy autonomous agent-based systems.

The role emphasizes Python engineering, LangChain/LangGraph, and integrating LLMs with enterprise data platforms, APIs, and scalable data lakes. You will collaborate with Data, ML, and Cloud teams to ensure guardrails, reliability, and cost efficiency.

Qualifications

• 5+ years in software or AI/ML engineering.
• Strong Python and asynchronous programming skills.
• Experience building LLM and generative AI applications.
• Experience with LangChain, LangGraph or similar agent frameworks.
• Knowledge of guardrails, responsible AI, security and failure handling.

Responsibilities

• Design and develop AI agent systems using LangChain, LangGraph, or similar frameworks.
• Build intelligent components capable of reasoning, planning, and autonomous task execution.
• Implement agentic patterns such as ReAct (Reasoning + Acting).
• Develop multi-step LLM workflows and agent orchestration.

Skills

Python

Async programming

LangChain

LangGraph

REST APIs

Cloud platforms

Data platforms

Problem solving

Team collaboration

Guardrails

Tools

LangChain

LangGraph

Snowflake

Databricks

APIs

Job description

We are seeking a highly skilled AI/LLM Engineer to design, develop, and deploy intelligent agent-based systems capable of reasoning, planning, and executing tasks autonomously. The ideal candidate will have strong Python engineering skills, hands‑on experience with modern AI agent frameworks, and experience integrating LLM solutions with enterprise data platforms.

Roles and Responsibilities

• Design and develop AI agent systems using LangChain, LangGraph, or similar frameworks.
• Build intelligent components capable of reasoning, planning, and autonomous task execution.
• Implement agentic patterns such as ReAct (Reasoning + Acting).
• Develop multi‑step LLM workflows and agent orchestration.

LLM Capabilities & Enhancements

• Implement memory, tool usage, context management, and MCP capabilities.
• Develop solutions using tool calling, chaining, and workflow orchestration.
• Work with prompt engineering teams to improve LLM response quality and performance.
• Optimize LLM applications for scalability, reliability, and cost.

Software Engineering

• Develop high‑quality, scalable, and maintainable Python applications, including asynchronous programming.
• Build and maintain APIs and microservices for AI and agent‑based applications.
• Integrate AI services with enterprise applications and backend systems.
• Develop production‑ready solutions with appropriate testing, monitoring, and error handling.

Guardrails & Responsible AI

• Design and implement guardrails and safety mechanisms for LLM‑powered applications.
• Handle edge cases, failures, hallucinations, and unintended model outputs.
• Implement appropriate validation, security, and access controls for AI systems.

Data & Platform Integration

• Integrate AI solutions with modern data platforms, including Snowflake and Databricks.
• Work with Lakehouse architectures and enterprise data pipelines.
• Enable LLM applications to securely access and leverage enterprise data.
• Collaborate with Data Engineering, ML Engineering, and Cloud teams on scalable AI architectures.

Required Technical Skills

• 5+ years of experience in software engineering, AI/ML engineering, or a related field.
• Strong hands‑on experience with Python and asynchronous programming.
• Experience building LLM and generative AI applications.
• Strong experience with LangChain, LangGraph, or similar agent frameworks.
• Understanding of AI agents, ReAct, tool calling, memory, context management, and MCP.
• Experience developing REST APIs and microservices.
• Experience integrating AI applications with Snowflake, Databricks, or Lakehouse platforms.
• Strong understanding of scalable, production‑ready software architectures.
• Knowledge of LLM guardrails, responsible AI, security, and failure handling.
• Strong problem‑solving, communication, and collaboration skills.

Preferred Skills

• Experience with multi‑agent systems and agent orchestration.
• Knowledge of vector databases and RAG architectures.
• Experience with cloud platforms such as AWS, Azure, or GCP.
• Familiarity with LLM observability, evaluation, and performance optimization.
• Experience deploying AI applications in enterprise production environments.